Lists (1)
Starred repositories
215
stars
written in Python
Clear filter
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
Universal and Transferable Attacks on Aligned Language Models
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
A language for constraint-guided and efficient LLM programming.
pocsuite3 is an open-sourced remote vulnerability testing framework developed by the Knownsec 404 Team.
Run PyTorch LLMs locally on servers, desktop and mobile
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and yo…
RAG that intelligently adapts to your use case, data, and queries
【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
Improved AnimateDiff for ComfyUI and Advanced Sampling Support
Let ChatGPT teach your own chatbot in hours with a single GPU!
Training and serving large-scale neural networks with auto parallelization.
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
Convert code repos into an LLM prompt-friendly format. Mostly built by GPT-4.
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
🖼️ Create beautiful maps from OpenStreetMap data in a streamlit webapp
Karras et al. (2022) diffusion models for PyTorch
A collaborative book on algorithms
OCR powered screen-capture tool to capture information instead of images
Extract files from any kind of container formats
[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…